Verteilung der zufällig gezogenen Messstellen

Die Verteilung des Anteils an landwirtschaflticher Fläche ähnelt der Gesamtverteilung.

## Random sampling
setDT(ezg_dt)
site_state2 = site_state[site_state$BL != 'SL', ] # keine EZG im Saarland
ns = setNames(site_state2$MST_190, site_state2$BL)
set.seed(12345678)
s1 = ezg_dt[ezg_dt[ ,
                     sample(x = .I,
                            size = ns[ match(unlist(.BY), names(ns)) ],
                            replace = FALSE),
                     by = 'state']$V1, ]

Verteilung der mit unterschiedlichen Wahrscheinlichkeiten gezogenen Messstellen

Da vermutet wird, dass mit absteigender EZG-Größe die Anzahl der EZG steigt, werden kleine EZG bei der Ziehung stärker gewichtet.

Messstellen nahe Landau

Catchments in a 50km circumference of Landau

# German cities

if (online) {
  drv = dbDriver('PostgreSQL')
  con = dbConnect(drv, user = DBuser, dbname = DBname_1, host = DBhost, port = DBport, password = DBpassword)
# Why is it so slow???!! https://github.com/r-spatial/sf/issues/503
#pl = st_read_db(con, query = "SELECT * FROM spatial_derived.germany_places")
  pl = get_postgis_query(con, "SELECT * FROM spatial_derived.germany_places WHERE name ILIKE 'Landau%'", geom_name = 'geom')
  pl = st_as_sf(pl)
  
  invisible(dbDisconnect(con))
  invisible(dbUnloadDriver(drv))
  
  saveRDS(pl, file.path(cachedir, 'places_germany.rds'))
  
} else {
  pl = readRDS(file.path(cachedir, 'places_germany.rds'))  
}
# grep Ladau
ld = pl[grep('Landau.+Pfalz', pl$name), ]

# Intersect catchments in a 50km circumference of Landau
st_crs(ld) = st_crs(ezg) #! p4s not matching 100%, change this in DB

## Warning: st_crs<- : replacing crs does not reproject data; use st_transform
## for that

ezg_ld_50 = ezg[unlist(st_intersects(st_buffer(ld, 50000), ezg)), ]

# interactive table
datatable(as.data.frame(ezg_ld_50)[ ,-7], caption = 'Catchments in a 50km circumference of Landau')

# manual selection
ezg_ld = c('RP_2375895800', 'RP_2378897000', 'RP_2391899300', 'BW_KR019.00')

# plot intersection area and all RP catchments
mapview(st_buffer(ld, 50000), color = 'goldenrod', lwd = 2, alpha.regions = 0,
        map.type = 'Esri.WorldImagery') +
  mapview(ezg[ezg$state %in% c('BW', 'HE', 'RP'), ], alpha.regions = 0.2, layer.name = 'EZG in BW, HE, RP') +
  mapview(ezg[ezg$site_id %in% ezg_ld, ], color = 'red', lwd = 3, layer.name = 'ausgewählte EZG')
datatable(as.data.frame(ezg)[ezg$site_id %in% ezg_ld, -7])

## Random sampling with probabilities
# thanks to
# https://stackoverflow.com/questions/17001808/generate-random-integers-between-two-values-with-a-given-probability-using-r
# ???
sample_list = list()
for (i in 1:length(names(ns))) {
  st = names(ns)[i]
  ezg_state = ezg_dt[ ezg_dt$state == st ]

  I1 = ezg_state[ , .I[area_sqkm <= 5]]
  I2 = ezg_state[ , .I[area_sqkm > 5 & area_sqkm <= 10]]
  I3 = ezg_state[ , .I[area_sqkm > 10 & area_sqkm <= 15]]
  I4 = ezg_state[ , .I[area_sqkm > 15 & area_sqkm <= 25]]
  I5 = ezg_state[ , .I[area_sqkm > 25 & area_sqkm <= 30]]
  
  L = sapply(list(I1, I2, I3, I4, I5), length); L
  
  set.seed(12345678)
  s2 = ezg_state[ezg_state[ ,
                            sample(x = c(I1, I2, I3, I4, I5),
                                   size = ns[ match(unlist(.BY), names(ns)) ],
                                   prob = rep(c(1/1.5, 1/4, 1/6, 1/9, 1/12) / L, L),
                                   replace = FALSE), 
                            by = state]$V1, ]
  sample_list[[i]] = data.table(s2)
  names(sample_list)[i] = st
}

## include manually picked EZGs close to Landau
manual_sel = as.data.table(ezg)[ ezg$site_id %in% ezg_ld, ][ , geometry := NULL ]
sample_list[['RP']][ site_id %in% c('RP_2397891300', 'RP_2375831900', 'RP_2522891900', 'RP_2699896100') ] = manual_sel
sample_dt = rbindlist(sample_list)

Karte der ausgewählten Einzugsgebiete

## Writing layer `ezg_ukl' to data source `/home/andreas/Desktop/ezg_ukl.shp' using driver `ESRI Shapefile'
## features:       2593
## fields:         6
## geometry type:  Multi Polygon

##           site_id site state            source area_sqkm atkis_perc
##    1:   SH_123755  mzb    SH image delineation      19.7       0.78
##    2: NI_37432228  mzb    NI image delineation       5.9       0.88
##    3: NI_48972700  mzb    NI image delineation       9.0       0.63
##    4:   SH_126643  mzb    SH image delineation       7.9       0.47
##    5: NI_48862918  mzb    NI image delineation      10.0       0.91
##   ---                                                              
## 2589:   ST_413719  psm    ST               DEM      28.3       0.82
## 2590:     TH_2227  psm    TH               DEM      19.8       0.82
## 2591:     TH_2546  psm    TH               DEM      29.9       0.51
## 2592:     TH_4058  psm    TH               DEM      18.7       0.55
## 2593: SN_OBF58002  psm    SN               DEM      28.2       0.73

Weitere (noch nicht beachtete) Auswahlkriterien

• Handynetz
• Abstand zwischen den Einzugsgebieten
• Kläranlagen